CN106067244A - A kind of sensor threshold value adaptive regulation method for perimeter detection system and system - Google Patents
A kind of sensor threshold value adaptive regulation method for perimeter detection system and system Download PDFInfo
- Publication number
- CN106067244A CN106067244A CN201610493500.2A CN201610493500A CN106067244A CN 106067244 A CN106067244 A CN 106067244A CN 201610493500 A CN201610493500 A CN 201610493500A CN 106067244 A CN106067244 A CN 106067244A
- Authority
- CN
- China
- Prior art keywords
- result
- sample
- eigenvalue
- module
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/20—Calibration, including self-calibrating arrangements
- G08B29/24—Self-calibration, e.g. compensating for environmental drift or ageing of components
- G08B29/26—Self-calibration, e.g. compensating for environmental drift or ageing of components by updating and storing reference thresholds
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of sensor threshold value adaptive regulation method for perimeter detection system and system, native system with the addition of the acquisition function to field samples storehouse on the basis of traditional detection systems, and utilize standard sample database, field samples storehouse that threshold values is re-started training, make system can classify and report to the police enclosing the behavior that sensor in boundary detects more accurately, including: receive the real time data gathered on circumference, from real time data, extract eigenvalue, and send eigenvalue；Combine current threshold values according to described eigenvalue calculate behavioral value result and send to client；Reception carries out the agenda result confirming to obtain according to described behavioral value result；The eigenvalue being currently entered is preserved as specific sample with agenda result, the most periodically specific sample is combined with master sample, go out real time threshold by Algorithm for Training, use real time threshold to substitute original threshold value.
Description
Technical field
The present invention relates to the sensor threshold value control method of a kind of perimeter detection system, particularly relate to a kind of for circumference
The sensor threshold value adaptive regulation method of detection system and system.
Background technology
Perimeter detection system is generally applied to the security protection in the places such as airport, warehouse, Factory Building, exhibition center, visits for circumference
Survey and the intellectuality of protection.Perimeter detection system adds sensing system, sensor on the basis of traditional video monitoring
System by various different external connection for the activity degree of being accelerated of circumference, vibration, the sense of the different aspects such as photosensitive and infrared
Should, the moving phase corresponding induced signal of various different external connection being formed with occurring on circumference, induced signal is reached the clothes of rear end
Business program is analyzed, stores and judges to notify Security Personnel by mobile radio terminal simultaneously, reminds Security Personnel couple
The practical situation of circumference carries out artificial confirmation, it is achieved circumference is carried out the technique effect of monitoring actively by sensor, solves
Determined intelligent detecting and monitoring circumference real-time condition technical problem.Conventional sensor comprises: Fibre Optical Sensor, inclination angle sensing
Device, vibrating sensor, infrared sensor, microwave radar, meteorological sensor etc..
The various kinds of sensors being arranged on circumference fence, demarcation line and enclosure wall is to not allowing the activity of type right on circumference
The induction information answered carries out real-time collection, and induction apparatus generates different types of sensing letter by gathering all types of induction informations
Number, the data in induced signal typically can be extracted as eigenvalue, and the system being arranged in back-end server is by these never
With in kind induced signal extract eigenvalue, each class behavior contingent on circumference is carried out signal aspect classification thus
Various effects and destruction that circumference is subject to by realization wake up with a start detection and supervision, and such as fence is bounced, circumference enclosure wall is played
Or suffer that hammering, week people out-of-bounds lean on circumference enclosure wall fence, circumference intercepts facility and knocked down etc. by external force.Traditional week
Boundary detection and monitoring system in order to the eigenvalue extracted in circumference information is carried out its for different behaviors classification, system
Algorithm design process all can use one or more groups threshold value set in advance eigenvalue is calculated.These are used for digital solution
The threshold value of analysis eigenvalue is before usually perimeter detection system is dispatched from the factory, and research staff or tester are at the laboratory environment of standard
The long-time collection of middle process, training draw.Prior art means are typically before system is dispatched from the factory to pass through in laboratory environment
Long-time collection, training draw threshold value.In other words, these threshold values are the optimal values reached based on laboratory environment.
But, specifically the environmental factors residing for each circumference can have certain difference with the test environment of laboratory, with
Also there is difference between the environment of the different sections of one circumference, under different weather conditions, have again difference, these actually used mistakes
In journey produce the various different in vitro tests of situation and training use test and training use-case set often without
Method is fully covered traversal.The density of such as wagon flow on zones of different peripheral path can the most not to the oscillation intensity of fence
With, frequent front, some regions is blown by high wind, and rainy day and fine day also have difference.These difference cause the threshold preset
Value is performed poor under some particular cases.
To sum up, the activity not allowing type on circumference is adopted by the various kinds of sensors in traditional perimeter detection and monitoring system
Collection, induction apparatus generates variety classes signal, is extracted as eigenvalue, to circumference detection and supervision, traditional perimeter detection and prison
Ore-controlling Role is in order to circumference information classification, all preset threshold value and calculate eigenvalue in algorithm.Threshold value is usually and passes
Before system system is dispatched from the factory, gathering in the lab, train and draw, these threshold values are the optimal values reached based on laboratory environment, but
Concrete environmental factors residing for each circumference can have certain difference, the difference of same circumference with the test environment of laboratory
The environment of section and different weather conditions etc. all can produce the error of eigenvalue, and these the in vitro test of situation is used
Example cannot fully be covered traversal, and these difference cause the threshold value preset to be performed poor under some particular cases, uses and passes
The perimeter detection of system technology and monitor system cannot realize the real-time update to circumference practical situation and accurately detection.
Summary of the invention
In view of the shortcoming of above prior art, it is an object of the invention to provide a kind of sensing for perimeter detection system
Device threshold adaptive control method and system, be used for solving existing predetermined threshold value and be not suitable with particular case, and threshold value cannot the most more
New technical problem.For achieving the above object and other relevant purposes, the present invention provides a kind of biography for perimeter detection system
Sensor threshold adaptive control method and system.A kind of threshold that can be automatically adjusted algorithm for this method according to actual sample
Being worth, described threshold value is classified for the behavior detecting sensor on circumference and reports to the police, including: adopt on S1, reception circumference
The real time data of collection, extracts eigenvalue from real time data, and sends eigenvalue；S2, draw behavior according to eigenvalue calculation
Testing result, draws behavioral value result according to described eigenvalue calculation and sends to client；S3, reception are according to described behavior
Testing result carries out the agenda result confirming to obtain；S4, using the eigenvalue of real data and agenda result as spy
Random sample is originally combined with master sample, draws comprehensive sample, according to comprehensive sample, uses Algorithm for Training to draw real time threshold, iteration
Real time threshold is used to update sensor threshold value, real time threshold and existing threshold value for the row judging that on circumference, sensor detects
For carrying out classifying and reporting to the police.
In one embodiment of the present invention, receive the real time data gathered on circumference, from real time data, extract spy
Value indicative, and send eigenvalue, including: receive sensing device and sense the different real time datas produced in different specific circumferences, in real time
Data are corresponding with the type information of the particular event occurred on circumference, eigenvalue containing type information.
In one embodiment of the present invention, draw behavioral value result according to eigenvalue calculation and send to client,
Including: send behavioral value result with the form of alarm.
In one embodiment of the present invention, using the eigenvalue of real data and agenda result as specific sample with
Master sample combines, and draws synthesis result, according to synthesis result and eigenvalue, uses Algorithm for Training to draw real time threshold, iteration
Use real time threshold to update existing threshold value, including: S41, the eigenvalue of real data and agenda result are added the first sample
This storehouse；S42, the first Sample Storehouse and the second Sample Storehouse random alignment are combined, obtain the 3rd sample set, the second Sample Storehouse stores
Master sample.S43, the 3rd sample set is stored in the 3rd Sample Storehouse；S44, using the behavior classification results of the 3rd Sample Storehouse as
Supervisory signals, using the eigenvalue of the 3rd Sample Storehouse as input variable, according to supervisory signals and input variable, is serviced by renewal
Program carries out threshold calculations to the 3rd Sample Storehouse, and iteration threshold calculates.
In one embodiment of the present invention, a kind of sensor threshold value Automatic adjusument side for perimeter detection system
Method, including: S1 ', reception behavior features testing result；S2 ', detecting generate reality about the input validation of described behavioral value result
Behavior outcome；S3 ', send described agenda result.
In one embodiment of the present invention, a kind of sensor threshold value Automatic adjusument for perimeter detection system services
Device 1, described threshold value is used for judging that the behavior that on circumference, sensor detects is classified and reports to the police, including: eigenvalue mould
Block 11, back-end services module 12, behavioral value result sending module 13, agenda result receiver module 14 and threshold value iteration mould
Block 15；Eigenvalue module 11, for receiving the real time data gathered on circumference, extracts eigenvalue, concurrently from real time data
Send eigenvalue；Back-end services module 12, for going on a journey as testing result according to eigenvalue calculation；Behavioral value result sending module
13, by manually verifying and confirming agenda result, raw into information according to the confirmation result of behavioral value result is given up really
Become agenda result；Agenda result receiver module 14, is used for receiving agenda result；Threshold value iteration module 15, uses
In being combined with master sample as specific sample with agenda result by the eigenvalue of real data, draw synthesis result, root
According to synthesis result and eigenvalue, drawing real time threshold, iteration uses real time threshold to update existing threshold value.
In one embodiment of the present invention, eigenvalue module 11, including: type information module 111 is mounted in front end
SCM Based module on fence, for receive in different specific circumference produce different real time datas, real time data with
The type information of the particular event occurred on circumference is corresponding, eigenvalue containing type information.
In one embodiment of the present invention, behavioral value result sending module 13, including: warning reminding module 131；Report
Alert prompting module 131 sends behavioral value result for the form with alarm.
In one embodiment of the present invention, threshold value iteration module 15, including: first sample memory module the 151, second sample
This memory module the 152, the 3rd sample memory module 153, iteration supervised training module 154；First sample memory module 151, uses
In agenda result is added the first Sample Storehouse；First Sample Storehouse is become as supervisory signals, input feature vector value as input
Amount；Second sample memory module 152, for the first Sample Storehouse and the second Sample Storehouse random alignment being combined, obtains the 3rd sample
Collection, stores master sample in the second Sample Storehouse.3rd sample memory module 153, for storage the 3rd Sample Storehouse；Iteration supervision instruction
Practice module 154, for using the behavior classification results of the 3rd Sample Storehouse as supervisory signals, using the eigenvalue of the 3rd Sample Storehouse as
Input variable, according to supervisory signals and input variable, carries out threshold calculations, iteration by updating service routine to the 3rd Sample Storehouse
Threshold calculations.
In one embodiment of the present invention, a kind of sensor threshold value Automatic adjusument terminal for perimeter detection system
Device 2, for obtaining the agenda result of perimeter detection system sensing object and being sent to server, including: behavioral value
Result receiver module 21, validating module 22, report to the police report editor module 23 and type of alarm sending module 24；Behavioral value is tied
Really receiver module 21, for reception behavior features testing result；Validating module 22, for by manually verifying and confirming agenda knot
Really；Report to the police and report editor module 23, for according to type of alarm composition warning report in agenda result；Type of alarm sends
Module 24, for sending agenda result with the form of report of reporting to the police, agenda result includes type of alarm.
As it has been described above, the present invention provide a kind of sensor threshold value adaptive regulation method for perimeter detection system and
System, has the advantages that
A kind of sensor threshold value adaptive regulation method for perimeter detection system provided by the present invention and system, its
The threshold value that algorithm draws dynamically updates, and has adaptive ability to different actual environments, and perimeter detection result has accuracy,
The sensor threshold value adaptive regulation method for perimeter detection system of present invention offer and system, solve existing circumference and visit
Predetermined threshold value in examining system is not suitable with particular case and threshold value cannot dynamically update the inaccurate technology of the perimeter detection caused
Problem.
Accompanying drawing explanation
Fig. 1 is shown as a kind of sensor threshold value adaptive regulation method step for perimeter detection system of the present invention and shows
It is intended to.
Fig. 2 is shown as sensor of the invention threshold value adaptive regulating step schematic diagram.
Fig. 3 is shown as the sensor mutual schematic diagram of self-adaptative adjustment interactive system of the perimeter detection system of the present invention.
Fig. 4 is shown as the sensor threshold value Automatic adjusument terminal method for perimeter detection system of the present invention and illustrates
Figure.
Fig. 5 is shown as a kind of sensor threshold value Automatic adjusument service unit mould for perimeter detection system of the present invention
Block schematic diagram.
Fig. 6 is shown as inventive feature value module diagram.
Fig. 7 is shown as the behavioral value result sending module schematic diagram of the present invention.
Fig. 8 is shown as the threshold value iteration module schematic diagram of the present invention.
Fig. 9 is shown as a kind of sensor threshold value Automatic adjusument termination for perimeter detection system of the present invention and shows
It is intended to.
Element numbers explanation
1 one kinds of sensor threshold value Automatic adjusument service units for perimeter detection system
11 eigenvalue modules
12 back-end services modules
13 behavioral value result sending modules
14 agenda result receiver modules
15 threshold value iteration module
111 type information modules
131 warning reminding modules
151 first sample memory modules
152 second sample memory modules
153 the 3rd sample memory modules
154 iteration supervised training modules
2 one kinds of sensor threshold value Automatic adjusument termination for perimeter detection system
21 behavioral value result receiver modules
22 validating modules
23 report to the police reports editor module
24 type of alarm sending modules
Step numbers explanation
Fig. 1 S1～S4
Fig. 2 S41～S44
Fig. 3 S1 '～S3 '
Detailed description of the invention
By particular specific embodiment, embodiments of the present invention being described below, those skilled in the art can be by this explanation
Content disclosed by book understands other advantages and effect of the present invention easily.
Refer to Fig. 1 to Fig. 9, it should however be clear that the structure depicted in this specification institute accompanying drawings, the most only in order to coordinate description institute
The content disclosed, understands for those skilled in the art and reads, being not limited to the enforceable qualifications of the present invention,
Therefore do not have technical essential meaning, and the modification of any structure, the change of proportionate relationship or the adjustment of size, do not affecting this
Under bright effect that can be generated by and the purpose that can reach, all should still fall and can contain at disclosed technology contents
In the range of.Meanwhile, in this specification cited as " on ", " under ", " left side ", " right side ", " centre " and " one " and etc. term, the most only
Understanding for ease of narration, and it is not used to limit the enforceable scope of the present invention, being altered or modified of its relativeness, without real
Under qualitative change more technology contents, when being also considered as the enforceable category of the present invention.
Refer to Fig. 1, be shown as a kind of sensor threshold value Automatic adjusument side for perimeter detection system of the present invention
Method step schematic diagram, as it is shown in figure 1, a kind of sensor threshold value adaptive regulation method for perimeter detection system, this method
Can be automatically adjusted the threshold value of algorithm according to actual sample, described threshold value is carried out for the behavior detecting sensor on circumference
Classification and reporting to the police, the sensor in perimeter detection system generally comprises Fibre Optical Sensor, obliquity sensor, vibrating sensor, red
Outer sensor, microwave radar and meteorological sensor etc., the threshold value of different sensors is at the algorithm of perimeter detection Yu monitoring system
Logic of propositions is configured as the judgement constant of Rule of judgment, when the circumference time related information of various types of sensor sensing exceedes this
The scope that threshold value is defined, perimeter detection system i.e. can determine that particular kind of sensor signal is abnormal, and system passes through this side
All kinds of events occurred on circumference are detected and monitor by formula, and it is a kind of for perimeter detection system that what the present invention provided include
Sensor threshold value adaptive regulation method comprises the following steps: the real time data gathered on S1, reception circumference, from real time data
Extracting eigenvalue, and send eigenvalue, described eigenvalue is relative from the circumference event signal of various different sensor sensings
Should, action, the hammering action of such as bounce circumference enclosure wall fence, playing, rely on and knock down etc. behavior, with corresponding eigenvalue pair
Should；S2, draw behavioral value result according to eigenvalue calculation, the testing result calculated by background service program by specific
Logic of propositions, calculate as input variable using eigenvalue, leave in corresponding memory unit as master sample；
S3, by manually verifying and confirming agenda result, according to the confirmation result of behavioral value result is given up raw into information really
Become agenda result, circumference nurse staff or perimeter detection testing crew to be received by portable customer terminal and
The alarm and reminding information that particular kind of behavioral value result is corresponding, and proceed to sense that particular event is sent out according to this information row
Raw sensor position confirms, and backend service program postbacks the agenda result of manual confirmation, and backstage takes
Business program receives the agenda result that caregiver is sent by client terminal；S4, sensor self-adaption regulation system will be real
The agenda result set that the eigenvalue of border data and user terminal feed back is deposited as the specific sample surveyed is original with system
The master sample collection of storage is combined, and draws the synthesis result that personnel's measured result is combined with standard testing result, according to comprehensively
Result and eigenvalue, use Algorithm for Training draw real time threshold, this real time threshold can according to varying environment and use condition to respectively
Sensor threshold value in kind of circumference carries out real-time update, after iteration uses real time threshold to update sensor threshold value, real time threshold and
Existing threshold value is used for judging that the behavior that on circumference, sensor detects is classified and reports to the police, the sensor threshold value in the present invention
As the important Rule of judgment in logic of propositions, according to said process, according to the continuous iteration of practical service environment, it is ensured that circumference is visited
Survey and the accuracy of monitoring.
Receive the real time data gathered on circumference, from real time data, extract eigenvalue, and send eigenvalue, including:
Receive sensing device and sense the different real time datas produced in different specific circumferences.
Obtain behavioral value result (i.e. the type information of event on circumference) according to eigenvalue calculation and send to client,
Including: send behavioral value result with the form of alarm.User's hands is held the user terminal apparatus that the present invention provides, is used for
During the anomalous event occurred on sensor sensing circumference, march to the circumference particular location that this anomalous event occurs in time, pass through
Artificial mode is to this event concrete condition and occurs positional information to confirm, test and caregiver are confirming specific week
After agenda result in battery limit (BL) section, i.e. by user terminal apparatus to perimeter detection and the server feedback of monitoring system
Agenda result, agenda result is stored to actual measurement behavior outcome set by server end, and the supervision for system contacts standard
Standby specific sample storehouse.
Refer to Fig. 2 and Fig. 3, be shown as sensor of the invention threshold value adaptive regulating step schematic diagram and the week of the present invention
The sensor mutual schematic diagram of self-adaptative adjustment interactive system of boundary's detection system, as shown in Figures 2 and 3, by the spy of real data
Value indicative is combined with master sample as specific sample with agenda result, and the mode that feature sample combines with master sample is preferred
Carrying out for random alignment compound mode, after permutation and combination draws synthesis result, perimeter detection and monitoring system are according to comprehensive knot
The eigenvalue that fruit draws with analysis various kinds of sensors signal, calculates real time threshold by logic of propositions, and iteration uses in real time
Threshold value updates existing threshold value, including: S41, the eigenvalue of real data and agenda result adds the first Sample Storehouse, high by the
One Sample Storehouse is preferably specific feature sample memory module, for the actual measurement behavior outcome fed back user by termination
Storing, this actual measurement behavior outcome includes kind and the circumference section of event generation of sense events；S42, by the first sample
The detection result sets random alignment of actual measurement behavior outcome collection and the second Sample Storehouse in storehouse combines, and obtains the 3rd Sample Storehouse, and the 3rd
The preparation of the interative computation that Sample Storehouse is carried out for the threshold value of the subsequent step sensor corresponding to all kinds of events, the second Sample Storehouse
Middle storage master sample, in master sample storage be last iteration update sensor threshold value set, described threshold value is all deposited
Storage is in the data base of perimeter detection system, and data field information can pass ginseng amendment at any time.S43, the 3rd sample set is stored in
3rd Sample Storehouse；S44, using the behavior classification results of described 3rd Sample Storehouse as supervisory signals, by the feature of the 3rd Sample Storehouse
It is worth as input variable, according to supervisory signals and input variable, by updating service routine, the 3rd Sample Storehouse is carried out threshold value meter
Calculating, iteration threshold calculates, and after single iteration computing completes, the threshold value of various kinds of sensors dynamically can be adjusted according to actual use environment
Joint once, and in upper once detection and threshold adjustment process as the particular decision condition of circumference sensor in back-end services journey
Sequence uses.
Refer to Fig. 4, be shown as the sensor threshold value Automatic adjusument terminal side for perimeter detection system of the present invention
Method schematic diagram, as shown in Figure 4, a kind of sensor threshold value adaptive regulation method for perimeter detection system, including: S1 ', connect
Receiving behavioral value result, the termination in the present invention receives the behavioral value result that perimeter detection system server is sent, should
Result includes the classification of generation event and concrete circumference respective section；S2 ', tie by manually verifying and confirming agenda
Really, user of service marches to report to the police accordingly section or the concrete outcome of camera head confirmation generation event；S3 ', user of service's root
Report to the police according to the type of alarm composition in the agenda result confirmed and report；S4 ', the form reported to report to the police send agenda
As a result, agenda result includes type of alarm, type of alarm and various types of sensors and all kinds of specific circumference thing
Part is corresponding, as the reference of dynamically adjustment sensor threshold value, sends the server to perimeter detection system.
Referring to Fig. 5, a kind of sensor threshold value Automatic adjusument for perimeter detection system being shown as the present invention takes
Business apparatus module schematic diagram, as it is shown in figure 5, a kind of sensor threshold value Automatic adjusument service unit for perimeter detection system
1, described threshold value is for judging that the behavior that on circumference, sensor detects is classified and reports to the police, for perimeter detection system
Sensor threshold value Automatic adjusument, including: eigenvalue module 11, back-end services module 12, behavioral value result sending module 13,
Agenda result receiver module 14 and threshold value iteration module 15；Eigenvalue module 11 communicates to connect with back-end services module 12,
For receiving the real time data gathered on circumference, from real time data, extract eigenvalue, and send eigenvalue, be arranged on Zhou Jie
Fence on obliquity sensor, vibrating sensor detection the tilt change value of fence, the intensity level of vibration, the meteorology of circumference
Sensor also can gather Carry Meteorological data, extracts eigenvalue and sends eigenvalue to back-end services program；Back-end services mould
Block 12, for going on a journey as testing result according to eigenvalue calculation；Behavioral value result sending module 13, by manually verifying and confirming
Agenda result, generates agenda result according to really giving up the confirmation result of behavioral value result into information；Actual
Behavior outcome receiver module 14, is used for receiving agenda result；Threshold value iteration module 15, for by the feature of real data
Value is combined with master sample as specific sample with agenda result, draws synthesis result, according to synthesis result and eigenvalue,
Drawing real time threshold, iteration uses real time threshold to update existing threshold value, according to synthesis result and eigenvalue, draws real time threshold,
This real time threshold can carry out real-time update according to varying environment and use condition to the sensor threshold value in various circumferences, and iteration makes
After updating sensor threshold value with real time threshold, real time threshold and existing threshold value are for the row judging that on circumference, sensor detects
For carrying out classifying and reporting to the police.
Refer to Fig. 6, be shown as inventive feature value module diagram, as shown in Figure 6, eigenvalue module 11, including:
The SCM Based module that type information module 111 is mounted on front end fence, is used for receiving in different specific circumference product
Raw different real time datas, real time data is corresponding with the type information of the particular event occurred on circumference, eigenvalue containing type
Information, type information includes bouncing circumference fence, plays, steps on, hammering, knock down and other kinds circumference event.
Refer to Fig. 7, be shown as the behavioral value result sending module schematic diagram of the present invention, as it is shown in fig. 7, behavioral value
Result sending module 13, including: warning reminding module 131；Warning reminding module 131 is for sending behavior inspection with the form of alarm
Survey result.Warning information includes all kinds of particular events occurred on circumference, and as external force pushes and shock etc., and these are specific
The real time information that event occurs, such as place and event, produces the behavior outcome of actual measurement for reminding specific personnel to confirm.
Refer to Fig. 8, be shown as the threshold value iteration module schematic diagram of the present invention, as shown in Figure 8, threshold value iteration module 15,
Including: first sample memory module the 151, second sample memory module the 152, the 3rd sample memory module 153, iteration supervised training
Module 154；First sample memory module 151, is used for adding storage agenda result；Second sample memory module 152, is used for
Storage master sample, and combine with the specific sample random alignment in the first sample memory module, obtain the 3rd sample set.3rd
Sample memory module 153, for storage the 3rd Sample Storehouse；Iteration supervised training module 154, for by the behavior of the 3rd Sample Storehouse
Classification results is as supervisory signals, using the eigenvalue of the 3rd Sample Storehouse as input variable, according to supervisory signals and input variable,
By updating service routine, the 3rd sample set is carried out threshold calculations, threshold calculations process loop iteration.Specific sample storehouse and
The content random alignment combination of standard sample database obtains a comprehensive Sample Storehouse, then this Sample Storehouse is put into nerve network system
Carrying out Training and test, input the eigenvalue for inputting each time, supervisory signals is the actual measurement behavior knot that user confirms
Really, training is output as new threshold value.
Refer to Fig. 9, be shown as a kind of sensor threshold value Automatic adjusument for perimeter detection system of the present invention eventually
End device schematic diagram, as it is shown in figure 9, a kind of sensor threshold value Automatic adjusument termination 2 for perimeter detection system, uses
In obtaining the agenda result of perimeter detection system sensing object and being sent to server, including: behavioral value result receives
Module 21, validating module 22, report to the police report editor module 23 and type of alarm sending module 24；Behavioral value result receiver module
21, for reception behavior features testing result；Validating module 22, for by manually verifying and confirming agenda result；Report to the police and report
Editor module 23, reports for reporting to the police according to type of alarm composition in agenda result；Type of alarm sending module 24, is used for
Sending agenda result with the form of report of reporting to the police, agenda result includes type of alarm.Send with the form of alarm
Behavioral value result.User's hands is held the user terminal apparatus that the present invention provides, for occurring on sensor sensing circumference
Anomalous event time, march in time this anomalous event occur circumference particular location, by the way of artificial, this event is had
Body situation and generation positional information confirm.
In sum, the present invention provide a kind of sensor threshold value adaptive regulation method for perimeter detection system and
System, the various kinds of sensors in the present invention generates variety classes signal to the live acquisition not allowing type on circumference, induction apparatus,
It is extracted as eigenvalue, circumference be detected and supervision, traditional perimeter detection and monitoring system be in order to circumference information classification, calculate
Introducing three Sample Storehouses in method, during wherein actual result and testing result are respectively stored in two samples, background service program is led to
Cross the combination of the two sample random alignment and the supervised training of iteration, be dynamically updated in the present invention for perimeter detection system
Sensor threshold value self-adaption regulation system in dynamic threshold, this dynamic threshold is not before legacy system dispatches from the factory, at laboratory
Middle collection, training draw, these threshold values are to reach optimal value based on laboratory environment, but system is according to different practical situations
It is iterated the threshold value updated, different use environment and condition are had dynamic and adaptive ability, each circumference
Residing environmental factors all can have certain difference with the test environment of laboratory, the environment of the different sections of same circumference and not
Same weather conditions etc. all can produce the error of eigenvalue, and these situation test case in the conventional technology cannot be filled
Divide and cover traversal, permissible at the sensor threshold value adaptive regulation method for perimeter detection system provided by invention and system
The interference of result of detection is significantly reduced by the most above-mentioned extraneous uncertainty, solves conventional art because these difference cause pre-
If threshold value under some particular cases, be not suitable with different practical service environments, the one that the present invention provides is for perimeter detection
The sensor threshold value adaptive regulation method of system and system can realize the self adaptation to circumference practical situation and accurately detection.Its
Middle predetermined threshold value has higher dynamic, and perimeter detection result has the technological merit of accuracy, has the highest commercial value
And practicality.
Claims (10)
1., for a sensor threshold value adaptive regulation method for perimeter detection system, this method can according to actual sample certainly
Moving the threshold value of regulation algorithm, described threshold value is classified for the behavior detecting sensor on circumference and reports to the police, its feature
Being, described method includes:
Receive the real time data gathered on circumference, from described real time data, extract eigenvalue；
Draw behavioral value result according to described eigenvalue calculation and send to client；
Reception carries out the agenda result confirming to obtain according to described behavioral value result；
The eigenvalue of real data is combined with master sample as specific sample with described agenda result, draws comprehensive knot
Really, according to described synthesis result and described eigenvalue, using Algorithm for Training to draw real time threshold, iteration uses described real time threshold
Update sensor threshold value.
Method the most according to claim 1, it is characterised in that the real time data gathered on described reception circumference, from described
Real time data extracts eigenvalue, and sends described eigenvalue, including: receive sensing device and sense product in different specific circumferences
The raw described real time data of difference, described real time data is corresponding with the type information of the particular event occurred on circumference, described spy
Value indicative comprises described type information.
Method the most according to claim 1, it is characterised in that described show that behavioral value is tied according to described eigenvalue calculation
Fruit also sends to client, including: send described behavioral value result with the form of alarm.
Method the most according to claim 1, using the eigenvalue of real data and described agenda result as specific sample
This is combined with master sample, draws synthesis result, according to described synthesis result and described eigenvalue, uses Algorithm for Training to draw reality
Time threshold value, iteration use described real time threshold update existing threshold value, it is characterised in that including:
The eigenvalue of real data and described agenda result are added the first Sample Storehouse；
Sample set random alignment in described first Sample Storehouse and the second Sample Storehouse is combined, obtains the 3rd sample set, described the
Two Sample Storehouses store master sample；
Described 3rd sample set is stored in the 3rd Sample Storehouse；
Using the behavior classification results of described 3rd Sample Storehouse as supervisory signals, using the eigenvalue of described 3rd Sample Storehouse as defeated
Enter variable；According to described supervisory signals and described input variable, by updating service routine, the 3rd Sample Storehouse is carried out threshold value meter
Calculate, threshold calculations described in iteration.
5. the sensor threshold value adaptive regulation method for perimeter detection system, it is characterised in that including:
Reception behavior features testing result；
Detect the input validation about described behavioral value result and generate agenda result；
Send described agenda result.
6., for a sensor threshold value self-adaptive regulating for perimeter detection system, described threshold value is for judging circumference
The behavior that sensor detects carries out classifying and reporting to the police, it is characterised in that adaptive for the sensor threshold value of perimeter detection system
Should regulate, including: eigenvalue module, back-end services module, behavioral value result sending module, agenda result receiver module
With threshold value iteration module；
Described eigenvalue module, for receiving the real time data gathered on circumference, extracts eigenvalue from described real time data,
And send described eigenvalue；
Described back-end services module, for going on a journey as testing result according to described eigenvalue calculation；
Described behavioral value result sending module, by manually verifying and confirming described agenda result, according to described behavior
The confirmation result of testing result is really given up and is generated agenda result into information；
Described agenda result receiver module, is used for receiving described agenda result；
Described threshold value iteration module, for using the eigenvalue of real data with described agenda result as specific sample and mark
Quasi-sample combines, and draws synthesis result, according to described synthesis result and described eigenvalue, draws real time threshold, and iteration uses institute
State real time threshold and update existing threshold value.
Device the most according to claim 6, it is characterised in that described real time data receiver module, including: type information mould
Block, for receiving the described real time data of difference produced in different specific circumference, described real time data and the spy of generation on circumference
The type information determining event is corresponding, and described eigenvalue comprises described type information.
Device the most according to claim 6, it is characterised in that described transmission response test module, including: warning reminding mould
Block；Described warning reminding module sends described behavioral value result for the form with alarm.
Device the most according to claim 6, it is characterised in that described threshold value iteration module, including: the first sample storage mould
Block, the second sample memory module, the 3rd sample memory module, iteration supervised training module；
Described first sample memory module, for using the eigenvalue of real data with described agenda result as the first sample
Storehouse；
Described second sample memory module, is used for storing master sample, described first Sample Storehouse and the second Sample Storehouse is arranged at random
Row combination, obtains the 3rd Sample Storehouse.
Described 3rd sample memory module, for storage the 3rd Sample Storehouse.
Described iteration supervised training module, is used for the behavior classification results of described 3rd Sample Storehouse as supervisory signals, input
The eigenvalue of described 3rd Sample Storehouse, as input variable, according to described supervisory signals and described input variable, is taken by renewal
Business program carries out threshold calculations to the 3rd Sample Storehouse, threshold calculations described in iteration.
10. the sensor threshold value self-adaptive regulating for perimeter detection system, it is characterised in that be used for obtaining circumference
The detection system sensing agenda result of object is also sent to server, including: behavioral value result receiver module, examines mould
Block, report to the police report editor module and type of alarm sending module；
Described behavioral value result receiver module, for reception behavior features testing result；
Described validating module, for by manually verifying and confirming agenda result；
Described report editor module of reporting to the police, for according to type of alarm composition warning report in described agenda result；
Described type of alarm sending module, for sending described agenda result, described reality with the form of described report of reporting to the police
Border behavior outcome includes type of alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610493500.2A CN106067244B (en) | 2016-06-29 | 2016-06-29 | A kind of sensor threshold value adaptive regulation method and system for perimeter detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610493500.2A CN106067244B (en) | 2016-06-29 | 2016-06-29 | A kind of sensor threshold value adaptive regulation method and system for perimeter detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106067244A true CN106067244A (en) | 2016-11-02 |
| CN106067244B CN106067244B (en) | 2018-08-17 |
Family
ID=57421302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610493500.2A Expired - Fee Related CN106067244B (en) | 2016-06-29 | 2016-06-29 | A kind of sensor threshold value adaptive regulation method and system for perimeter detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106067244B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781341A (en) * | 2016-12-27 | 2017-05-31 | 公安部第三研究所 | A kind of vibration simulation system, method and vibration test system |
| CN108234157A (en) * | 2016-12-13 | 2018-06-29 | 国基电子（上海）有限公司 | Noise management method and management server |
| CN108289049A (en) * | 2017-01-09 | 2018-07-17 | 佛山市顺德区美的电热电器制造有限公司 | The peculiar odor treatment method and household appliance to link between household electrical appliances |
| CN108984370A (en) * | 2018-07-13 | 2018-12-11 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of determining monitoring threshold value |
| CN110046182A (en) * | 2019-03-21 | 2019-07-23 | 华能澜沧江水电股份有限公司 | A kind of huge hydroelectric power plant's intelligent alarm threshold setting method and system |
| CN110084986A (en) * | 2019-04-29 | 2019-08-02 | 西人马（厦门）科技有限公司 | A kind of circumference safety protection method and device |
| CN110164071A (en) * | 2019-04-29 | 2019-08-23 | 西人马（厦门）科技有限公司 | A kind of security system |
| CN110517438A (en) * | 2019-10-11 | 2019-11-29 | 四川长虹电器股份有限公司 | A kind of method and warning device of adaptive adjustment smoke alarm threshold value |
| CN110874674A (en) * | 2018-08-29 | 2020-03-10 | 阿里巴巴集团控股有限公司 | Anomaly detection method, device and equipment |
| CN111122841A (en) * | 2018-10-31 | 2020-05-08 | 深圳市帝迈生物技术有限公司 | Method for improving sample result accuracy and sample analyzer |
| CN111308058A (en) * | 2020-03-14 | 2020-06-19 | 深圳联开生物医疗科技有限公司 | Counting hole voltage alarm threshold self-adaption method and device and blood cell analyzer |
| CN112449362A (en) * | 2020-11-18 | 2021-03-05 | 中国科学院上海微系统与信息技术研究所 | Intelligent sensor self-adaptive configuration method, device and system based on letter model |
| CN112899969A (en) * | 2019-11-19 | 2021-06-04 | 青岛海尔智能技术研发有限公司 | Control method and device for washing machine and direct-current motor washing machine |
| CN113194297A (en) * | 2021-04-30 | 2021-07-30 | 重庆市科学技术研究院 | Intelligent monitoring system and method |
| CN114363148A (en) * | 2021-12-20 | 2022-04-15 | 绿盟科技集团股份有限公司 | Method, device, detection equipment and storage medium for detecting attack alarm |
| CN116798204A (en) * | 2023-08-14 | 2023-09-22 | 成都数智创新精益科技有限公司 | Security method, security device, security equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060232440A1 (en) * | 2005-08-02 | 2006-10-19 | Moreno Pieralli | Microwave Detection System and Method |
| CN101388130A (en) * | 2008-03-05 | 2009-03-18 | 中科院嘉兴中心微系统所分中心 | Multi-grade stereo anti-intruding system, apparatus and implementing method based on wireless sensing net |
| CN101556724A (en) * | 2008-04-09 | 2009-10-14 | 中国科学院半导体研究所 | Safety management system of optical fiber perimeter and pattern recognition method thereof |
| CN101840615A (en) * | 2010-04-09 | 2010-09-22 | 武汉理工大学 | Self-adaptive warning system for intelligently addressing circumferential intrusions of fiber Bragging grating |
| CN101930649A (en) * | 2010-08-20 | 2010-12-29 | 宁波诺可电子科技发展有限公司 | Method for preventing false alarm under severe weather conditions for fiber fence alarm system |
| CN102708384A (en) * | 2012-06-04 | 2012-10-03 | 西南交通大学 | Bootstrapping weak learning method based on random fern and classifier thereof |
| CN104580896A (en) * | 2014-12-25 | 2015-04-29 | 深圳市锐明视讯技术有限公司 | Method and device for switching day and night modes of camera |
| CN104949705A (en) * | 2015-06-18 | 2015-09-30 | 昂纳信息技术（深圳）有限公司 | Method for dynamically adjusting threshold of optical fiber sensor |
| CN105608823A (en) * | 2016-03-14 | 2016-05-25 | 北京北邮国安技术股份有限公司 | Optical fiber security and protection method and system based on principal component analysis |
| CN105654645A (en) * | 2016-01-22 | 2016-06-08 | 北京北邮国安技术股份有限公司 | Optical fiber security and protection signal processing method and system |
-
2016
- 2016-06-29 CN CN201610493500.2A patent/CN106067244B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060232440A1 (en) * | 2005-08-02 | 2006-10-19 | Moreno Pieralli | Microwave Detection System and Method |
| CN101388130A (en) * | 2008-03-05 | 2009-03-18 | 中科院嘉兴中心微系统所分中心 | Multi-grade stereo anti-intruding system, apparatus and implementing method based on wireless sensing net |
| CN101556724A (en) * | 2008-04-09 | 2009-10-14 | 中国科学院半导体研究所 | Safety management system of optical fiber perimeter and pattern recognition method thereof |
| CN101840615A (en) * | 2010-04-09 | 2010-09-22 | 武汉理工大学 | Self-adaptive warning system for intelligently addressing circumferential intrusions of fiber Bragging grating |
| CN101930649A (en) * | 2010-08-20 | 2010-12-29 | 宁波诺可电子科技发展有限公司 | Method for preventing false alarm under severe weather conditions for fiber fence alarm system |
| CN102708384A (en) * | 2012-06-04 | 2012-10-03 | 西南交通大学 | Bootstrapping weak learning method based on random fern and classifier thereof |
| CN104580896A (en) * | 2014-12-25 | 2015-04-29 | 深圳市锐明视讯技术有限公司 | Method and device for switching day and night modes of camera |
| CN104949705A (en) * | 2015-06-18 | 2015-09-30 | 昂纳信息技术（深圳）有限公司 | Method for dynamically adjusting threshold of optical fiber sensor |
| CN105654645A (en) * | 2016-01-22 | 2016-06-08 | 北京北邮国安技术股份有限公司 | Optical fiber security and protection signal processing method and system |
| CN105608823A (en) * | 2016-03-14 | 2016-05-25 | 北京北邮国安技术股份有限公司 | Optical fiber security and protection method and system based on principal component analysis |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108234157A (en) * | 2016-12-13 | 2018-06-29 | 国基电子（上海）有限公司 | Noise management method and management server |
| CN106781341A (en) * | 2016-12-27 | 2017-05-31 | 公安部第三研究所 | A kind of vibration simulation system, method and vibration test system |
| CN106781341B (en) * | 2016-12-27 | 2020-04-14 | 公安部第三研究所 | Vibration simulation system and method and vibration test system |
| CN108289049A (en) * | 2017-01-09 | 2018-07-17 | 佛山市顺德区美的电热电器制造有限公司 | The peculiar odor treatment method and household appliance to link between household electrical appliances |
| CN108984370B (en) * | 2018-07-13 | 2022-02-01 | 北京京东尚科信息技术有限公司 | Method and device for determining monitoring threshold |
| CN108984370A (en) * | 2018-07-13 | 2018-12-11 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of determining monitoring threshold value |
| CN110874674A (en) * | 2018-08-29 | 2020-03-10 | 阿里巴巴集团控股有限公司 | Anomaly detection method, device and equipment |
| CN110874674B (en) * | 2018-08-29 | 2023-06-27 | 阿里巴巴集团控股有限公司 | Abnormality detection method, device and equipment |
| CN111122841A (en) * | 2018-10-31 | 2020-05-08 | 深圳市帝迈生物技术有限公司 | Method for improving sample result accuracy and sample analyzer |
| CN110046182A (en) * | 2019-03-21 | 2019-07-23 | 华能澜沧江水电股份有限公司 | A kind of huge hydroelectric power plant's intelligent alarm threshold setting method and system |
| CN110164071A (en) * | 2019-04-29 | 2019-08-23 | 西人马（厦门）科技有限公司 | A kind of security system |
| CN110084986A (en) * | 2019-04-29 | 2019-08-02 | 西人马（厦门）科技有限公司 | A kind of circumference safety protection method and device |
| CN110084986B (en) * | 2019-04-29 | 2021-11-09 | 西人马联合测控（泉州）科技有限公司 | Perimeter security method and device |
| CN110517438A (en) * | 2019-10-11 | 2019-11-29 | 四川长虹电器股份有限公司 | A kind of method and warning device of adaptive adjustment smoke alarm threshold value |
| CN112899969A (en) * | 2019-11-19 | 2021-06-04 | 青岛海尔智能技术研发有限公司 | Control method and device for washing machine and direct-current motor washing machine |
| CN112899969B (en) * | 2019-11-19 | 2023-09-19 | 青岛海尔智能技术研发有限公司 | Control method and device for washing machine and direct current motor washing machine |
| CN111308058A (en) * | 2020-03-14 | 2020-06-19 | 深圳联开生物医疗科技有限公司 | Counting hole voltage alarm threshold self-adaption method and device and blood cell analyzer |
| CN112449362A (en) * | 2020-11-18 | 2021-03-05 | 中国科学院上海微系统与信息技术研究所 | Intelligent sensor self-adaptive configuration method, device and system based on letter model |
| CN112449362B (en) * | 2020-11-18 | 2021-08-20 | 中国科学院上海微系统与信息技术研究所 | Intelligent sensor self-adaptive configuration method, device and system based on letter model |
| CN113194297B (en) * | 2021-04-30 | 2023-05-23 | 重庆市科学技术研究院 | Intelligent monitoring system and method |
| CN113194297A (en) * | 2021-04-30 | 2021-07-30 | 重庆市科学技术研究院 | Intelligent monitoring system and method |
| CN114363148A (en) * | 2021-12-20 | 2022-04-15 | 绿盟科技集团股份有限公司 | Method, device, detection equipment and storage medium for detecting attack alarm |
| CN114363148B (en) * | 2021-12-20 | 2023-05-26 | 绿盟科技集团股份有限公司 | Method, device, detection equipment and storage medium for detecting attack alarm |
| CN116798204A (en) * | 2023-08-14 | 2023-09-22 | 成都数智创新精益科技有限公司 | Security method, security device, security equipment and storage medium |
| CN116798204B (en) * | 2023-08-14 | 2023-11-03 | 成都数智创新精益科技有限公司 | Security method, security device, security equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106067244B (en) | 2018-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106067244A (en) | A kind of sensor threshold value adaptive regulation method for perimeter detection system and system | |
| US11910137B2 (en) | Processing time-series measurement entries of a measurement database | |
| CN105181898B (en) | Atmospheric pollution monitoring and management method as well as system based on high-density deployment of sensors | |
| JP5422859B2 (en) | Monitoring device and suspicious behavior detection method | |
| JPH06503421A (en) | Lightning forecasting equipment and method | |
| CN105931458B (en) | A kind of method of road traffic flow detection device reliability assessment | |
| CN109165779B (en) | Population quantity prediction method based on multi-source big data and long-short term memory neural network model | |
| CN101569194B (en) | Network surveillance system | |
| CN110213376A (en) | A kind of information processing system and method for pest prevention | |
| US11325777B2 (en) | Systems and processes for space management of three dimensional containers including biological measurements | |
| KR20200106764A (en) | System for predicting diseases and pest signs | |
| CN108732313A (en) | Urban air pollution object concentration intelligence observation system | |
| CN115100816A (en) | Wearable near-electricity sensing equipment and monitoring system | |
| Cheng et al. | Automatic incident detection for urban expressways based on segment traffic flow density | |
| US20200117840A1 (en) | Injection of simulated sources in a system of networked sensors | |
| CN105117767B (en) | Display screen attention rate statistical method and system | |
| CN116543540A (en) | Online intelligent monitoring and sensing system and sensing method for pool liquid level based on Internet of things | |
| CN109272230B (en) | Data quality evaluation method and system for atmospheric pressure element of ground observation station | |
| CN105222885B (en) | Optical fiber vibration detection method and device | |
| US11758307B2 (en) | Sensor device, background noise data transmission method, and background noise data transmission program | |
| CN116562672A (en) | Inspection work quality evaluation method and system | |
| Mak et al. | Development of dual-station automated expressway incident detection algorithms | |
| CN114646735A (en) | Carbon dioxide concentration monitoring system in air | |
| CN110294429A (en) | A kind of tower crane stabilization of equipment performance analysis system | |
| CN116739357B (en) | Multi-mode fusion perception city existing building wide area monitoring and early warning method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180309 Address after: 200050 Changning Road, Shanghai, No. 865, No. Applicant after: Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences Applicant after: University of Chinese Academy of Sciences Address before: 200050 Changning Road, Shanghai, No. 865, No. Applicant before: Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180817 Termination date: 20200629 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |